Přístupnostní navigace
E-application
Search Search Close
Publication detail
BŘEZINA, T. HOUŠKA, P. SINGULE, V.
Original Title
USAGE OF LEARNING IN FOUR-LEGGED ROBOT CONTROL
Type
conference paper
Language
English
Original Abstract
The report describes a possible method of discretization of the continuous status space of the four-legged robot using simultaneous compositions of effects of basic control elements. The compositions are activated from a non-deterministic terminal automatic machine. In the design stage it is possible to use simple considerations for significant limitation of the number of statuses of the terminal automatic machines and the number of possible simultaneous compositions. The valuation of transfers of the terminal automatic machine corresponds with compositions of control elements. For such a prepared scheme of transfers there is applied the variant of Q-learning so as to gradually specify the estimation of the future benefit from individual transfers and so as there are activated the simultaneous compositions of control elements with the maximal estimation of future benefit.
Keywords
Reinforcement learning, Q-learning, control of robots
Authors
BŘEZINA, T.; HOUŠKA, P.; SINGULE, V.
RIV year
2002
Released
24. 9. 2002
Publisher
Trenčianská univerzita Alexandra Dubčeka v Trenčíně
Location
Trenčín
ISBN
80-88914-73-6
Book
SEKEL 2002
Edition number
1
Pages from
87
Pages to
90
Pages count
4
BibTex
@inproceedings{BUT9662, author="Tomáš {Březina} and Pavel {Houška} and Vladislav {Singule}", title="USAGE OF LEARNING IN FOUR-LEGGED ROBOT CONTROL", booktitle="SEKEL 2002", year="2002", number="1", pages="4", publisher="Trenčianská univerzita Alexandra Dubčeka v Trenčíně", address="Trenčín", isbn="80-88914-73-6" }